检索结果-内蒙古大学图书馆

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Singh, Dinesh Kumar Sharma, Vishnu Fce Poornima University Department of Computer Science and Engineering Jaipur India Fce Poornima University Department of Computer Science and Application Jaipur India

ISBN: (纸本)9798331518592

Rural areas in India, such as Randullabad village in Satara, are facing significant water challenges related to UN SDG6. It includes inadequate water supply, inefficient distribution, and poor water quality. Current methods of water governance rely on manual data collection and limited use of sensors. This leads to lack of modelling, inaccurate estimation, delayed response times, and inefficient decision-making. These limitations results in water-related conflicts, water-wastage, and economic losses. To address these issues, a digital twin approach is proposed for sustainable water management. This approach integrates existing and historical data with new data from advanced sensors, using machine learning algorithms to create a virtual replica of the village's water supply network. The proposed methodology and high-level implementation architecture of Digital Twin of Randullabad Watershed and Groundwater (DToGW) could set new water-governance standards at the village level and potentially transform water management in rural communities. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Gabor Wavelet Based Fused Texture Features for Identification of Mungbean Leaf Diseases 1st

Gabor Wavelet Based Fused Texture Features for Identificati...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Majumder, Sarna Mazumder, Badhan Islam, S. M. Taohidul Faculty of Computer Science and Engineering Patuakhali Science and Technology University Patuakhali Bangladesh Department of Computer and Communication Engineering Patuakhali Science and Technology University Patuakhali Bangladesh Department of Computer Science and Engineering Dhaka International University Dhaka Bangladesh Department of Electrical and Electronics Engineering Patuakhali Science and Technology University Patuakhali Bangladesh

ISBN: (纸本)9783031346187

Early diagnosis of crop plant disease is crucial since many of these diseases pose a considerable threat not only to global food security but also towards agricultural productivity. Aiming that, for detection of mungbean leaf diseases at the beginning stage, we introduce a novel approach based on Gabor Wavelet Transform (GWT) and Cubic SVM in this paper. We perform GWT to decompose the given images into eighteen directional sub-bands and then extract fusion of Gabor Wavelet (GW) based texture features from each detailed GWT coefficient sub-band. Finally, Cubic SVM was deployed to classify three different disease classes by using these GW based features, conducting cross validation at 10 fold. Outcomes of our experimental evaluation using our self-prepared dataset of mungbean leaf diseases exhibit that our proposed method yields overall a sensitivity of 91.11%, a specificity of 95.56%, a precision of 91.39% and an accuracy of 91.11%. Moreover, outcomes obtained from our comparative analysis confirm the supremacy of our proposed framework over 3 currently existing approaches. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

GRAPHTRAIL: Translating GNN Predictions into Human-Interpretable Logical Rules 38

GRAPHTRAIL: Translating GNN Predictions into Human-Interpret...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Armgaan, Burouj Dalmia, Manthan Medya, Sourav Ranu, Sayan Department of Computer Science University of Illinois Chicago United States Department of Computer Science & Engineering Yardi School of AI IIT Delhi India

Instance-level explanation of graph neural networks (GNNs) is a well-studied area. These explainers, however, only explain an instance (e.g., a graph) and fail to uncover the combinatorial reasoning learned by a GNN from the training data towards making its predictions. In this work, we introduce GRAPHTRAIL, the first end-to-end, post-hoc, global GNN explainer that translates the functioning of a black-box GNN model to a boolean formula over the (sub)graph-level concepts without relying on local explainers. GRAPHTRAIL is unique in automatically mining the discriminative subgraph-level concepts using Shapley values. Subsequently, the GNN predictions are mapped to a human-interpretable boolean formula over these concepts through symbolic regression. Extensive experiments across diverse datasets and GNN architectures demonstrate significant improvement over existing global explainers in mapping GNN predictions to faithful logical formulae. The robust and accurate performance of GRAPHTRAIL makes it invaluable for improving GNNs and facilitates adoption in domains with strict transparency requirements. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social Media Interaction-Based Mental Health Analysis with a Chat-Bot User Interface 8th

Social Media Interaction-Based Mental Health Analysis with a...

引用

8th International Conference on Emerging Research in Computing, Information, Communication and Applications, ERCICA 2023

作者： Kabeer, Aliyah John, Paul Gomez, Serena A. Agarwal, Pooja Ananthanagu, U. Department of Computer Science and Engineering PES University Bangalore India

ISBN: (纸本)9789819976218

In recent times, social media has played a major role in shaping the state of mind of young adults. This means that the content that is interacted with online may subconsciously have a significant effect on one’s mental health. This paper presents a novel approach to detect the mental health state of a user by analyzing their online activity over a period of time and generating a report indicating the same. The user is then allowed to ask any clarifying questions on the generated report, along with general queries on mental health via a chat-bot interface. In order to classify the mental state of the user based on the kind of content posted or interacted with by them, their tweets are scraped and feature vectors of the same are generated. Supervised machine learning algorithms like Support Vector Machines (SVM) and neural network-based models like Long Short-Term Memory (LSTM) are compared for their performance on prediction. A transfer learning approach is also attempted and gives promising results in predicting the classes of the tweets. Natural Language Processing techniques such as question similarity and extractive summarization are utilized in building the chat-bot framework. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Chatbot Mental health Question similarity Report Social media Tweets Twitter

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hindi Handwriting Recognition Using Neural Network 2

Enhancing Hindi Handwriting Recognition Using Neural Network

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Yadav, Narinder Gagandeep Kumar, Mayank Yadav, Shivanshu Ronit Megha Chandigarh University Department of Computer science and engineering Punjab India

ISBN: (纸本)9798331519056

With an emphasis on datasets containing the Devanagari script-the writing system used for the Hindi language-this research explores the application of sophisticated neural network techniques to improve the recognition of Hindi handwriting. Optical character recognition systems, which are used in automated form processing, historical manuscript digitisation, and educational programs, depend heavily on handwriting recognition. Conventional recognition techniques frequently lack the robustness and accuracy needed to handle intricate scripts like Devanagari. To increase the accuracy of Hindi handwritten text identification, we employ a number of cutting-edge neural network models in this study, including Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), which are specially designed for the Devanagari script. Our tests show notable gains over baseline models, highlighting the significance of well-optimized network designs and training protocols. We also explore the implications of these results for practical applications and future directions in the field of Hindi handwriting recognition systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DynaFog: A Dynamic Task Offloading Framework for IoT-Based Fog Computing Platforms 13

DynaFog: A Dynamic Task Offloading Framework for IoT-Based F...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Tripathy, Subhranshu Sekhar Bebortta, Sujit Mukherjee, Tanmay School of Computer Engineering Kiit Deemed to Be University Bhubaneswar751024 India Ravenshaw University Department of Computer Science Cuttack753003 India University Department of Computer Science and Engineering Bhubaneswar751030 India

ISBN: (纸本)9798350305463

This paper explores the complexities of task offloading in a dynamic fog computing network, where multihop Internet of Things (IoT) access points (APs) support the connectivity between IoT devices and fog computing nodes. The suggested DynaFog framework is organised around key elements in the context of IoT architectures based on fog computing. These components include the selection of fog nodes with skill, the optimization of paths for effective offloading, and the best decision-making about local or remote task computation. We carefully formulated the task offloading problem over a multi-hop communication link by considering an integer linear program (ILP) in order to handle this intricate scenario. Owing to the non-convexity of the possible solution set, a greedy approach-driven heuristic strategy has been proposed to efficiently navigate the problem space. The technique for the solution incorporates a holistic viewpoint that covers multi-hop routing, energy utilization, delay, and dynamic network characteristics, particularly with regard to utilization of link and fog controllers' capacity. Our experimental results validate the effectiveness of the suggested strategy, demonstrating a noteworthy decrease in average delay and energy usage in comparison to benchmarks. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

引用

computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan Md.Siraj Jia Uddin Department of Computer Science and Engineering BRAC UniversityDhaka1212Bangladesh Department of AI and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

来源：评论

学校读者我要写书评

暂无评论

Generating synthetic mixed-type tabular data by decoding samples from a latent-space: a case study in healthcare 28th

Generating synthetic mixed-type tabular data by decoding sam...

引用

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Drapala, Jaroslaw Swiatek, Jerzy Department of Computer Science and Systems Engineering Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wroclaw50-370 Poland

Medical data are subject to privacy regulations, which severely limit AI specialists who wish to construct decision support systems for medicine. Large amounts of this data are tabular, indicating that they are organized into a table format, where patient records are represented in rows and measured variables in columns. Furthermore, the variables come in different types-some are numerical, while others are categorical. In this work, we introduce a novel method for constructing generators of synthetic tabular data with mixed types. The key point of our approach is the explicit utilization of a latent space to represent the original data. A case study using real medical data is presented. © 2024 The Authors.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Evolving Approaches in Epilepsy Management: Harnessing Internet of Things and Deep Learning 6th

Evolving Approaches in Epilepsy Management: Harnessing Inter...

引用

6th International conference on communication and computational technologies, ICCCT 2024

作者： Assim, Ola Marwan Mahmood, Ahlam Fadhil Department of Computer Science Engineering University of Mosul Mosul Iraq

ISBN: (纸本)9789819774227

For efficient treatment and management of epilepsy, which is characterized by repeated, abrupt, and excessive electrical discharges in the brain, early detection and exact diagnosis are required. The use of the Internet of Things (IoT) and deep learning algorithms for identifying and monitoring epileptic seizures has increased dramatically in recent years. IoT devices, which collect data from various sources like video cameras, wearable sensors, and electroencephalogram (EEG) equipment, collaborate with deep learning algorithms to deliver real-time insights about a patient's status. This in-depth examination examines the most recent breakthroughs in IoT and deep learning technology for identifying and tracking epileptic episodes. The review delves into the field's existing issues and potential future directions. This review begins by discussing the intricacies of diagnosing and monitoring epilepsy and subsequently delving into IoT and deep learning techniques for seizure detection, classification, and prediction. Finally, we shed light on intriguing research avenues and discuss the barriers and prospects in this dynamic domain. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Twitter Disaster Prediction Using Different Deep Learning Models

引用

SN computer science 2024年第1期5卷 179页

作者： Duraisamy, Premkumar Natarajan, Yuvaraj Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamil Nadu Coimbatore India

In emergencies, Twitter has become an essential way for people to communicate. Since many people use smartphones, they can easily report events they see. Because of this, more organizations are using Twitter to monitor what is happening digitally. Twitter and similar online platforms provide a place to share their personal experiences and local events with others. People often post about their daily lives, things happening in their neighborhoods, and their activities to keep others informed. In this study, we focus on predicting disasters on Twitter using an improved Bidirectional Encoder Depiction from the Transformers (BERT) model. Twitter has become a crucial communication tool during emergencies, allowing people to report events they witness quickly. As a result, organizations are increasingly using Twitter for digital monitoring. Our research utilizes a modified version of the BERT model, a powerful language representation technique. This modified BERT model enables us to understand better tweets related to disasters and improve the accuracy of our predictions. Using Twitter data, we train our improved BERT model to recognize patterns and signals associated with different types of disasters, such as natural calamities or accidents. We aim to efficiently detect and respond to potential disasters in real time by doing so. Our experiments' results demonstrate our BERT effectiveness, showing improved disaster prediction performance compared to traditional models like the long short-term memory model (LSTM) and gated recurrent unit model (GRU). This research contributes valuable insights into disaster management strategies and allows leveraging social media data in disaster preparedness and response efforts. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Bidirectional encoder depiction from the transformers Gated recurrent unit model Long short-term memory model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：